Digital Commons Network^™

Performance Of Ct-Based Deep Learning In Diagnostic Assessment Of Suspicious Lateral Lymph Nodes In Papillary Thyroid Cancer: A Prospective Diagnostic Study, Guibin Zheng, Haicheng Zhang, Fusheng Lin, Mark Zafereo, Neil Gross, Peng Sun, Yang Liu, Haiqing Sun, Guochang Wu, Shujian Wei, Jia Wu, Ning Mao, Guojun Li, Guoyang Wu, Haitao Zheng, Xicheng Song

Faculty, Staff and Student Publications

Background: Preoperative evaluation of the metastasis status of lateral lymph nodes (LNs) in papillary thyroid cancer is challenging. Strategies for using deep learning to diagnosis of lateral LN metastasis require additional development and testing. This study aimed to build a deep learning-based model to distinguish benign lateral LNs from metastatic lateral LNs in papillary thyroid cancer and test the model's diagnostic performance in a real-world clinical setting.

Methods: This was a prospective diagnostic study. An ensemble model integrating a three-dimensional residual network algorithm with clinical risk factors available before surgery was developed based on computed tomography images of lateral LNs …

Deep Learning-Based Dose Prediction To Improve The Plan Quality Of Volumetric Modulated Arc Therapy For Gynecologic Cancers, Mary P Gronberg, Anuja Jhingran, Tucker J Netherton, Skylar S Gay, Carlos E Cardenas, Christine Chung, David Fuentes, Clifton D Fuller, Rebecca M Howell, Meena Khan, Tze Yee Lim, Barbara Marquez, Adenike M Olanrewaju, Christine B Peterson, Ivan Vazquez, Thomas J Whitaker, Zachary Wooten, Ming Yang, Laurence E Court

Faculty, Staff and Student Publications

Background: In recent years, deep‐learning models have been used to predict entire three‐dimensional dose distributions. However, the usability of dose predictions to improve plan quality should be further investigated.

Purpose: To develop a deep‐learning model to predict high‐quality dose distributions for volumetric modulated arc therapy (VMAT) plans for patients with gynecologic cancer and to evaluate their usability in driving plan quality improvements.

Methods: A total of 79 VMAT plans for the female pelvis were used to train (47 plans), validate (16 plans), and test (16 plans) 3D dense dilated U‐Net models to predict 3D dose distributions. The models received the …

Real-Time Liver Motion Estimation Via Deep Learning-Based Angle-Agnostic X-Ray Imaging, Hua-Chieh Shao, Yunxiang Li, Jing Wang, Steve Jiang, You Zhang

Faculty, Staff and Student Publications

Background: Real-time liver imaging is challenged by the short imaging time (within hundreds of milliseconds) to meet the temporal constraint posted by rapid patient breathing, resulting in extreme under-sampling for desired 3D imaging. Deep learning (DL)-based real-time imaging/motion estimation techniques are emerging as promising solutions, which can use a single X-ray projection to estimate 3D moving liver volumes by solved deformable motion. However, such techniques were mostly developed for a specific, fixed X-ray projection angle, thereby impractical to verify and guide arc-based radiotherapy with continuous gantry rotation.

Purpose: To enable deformable motion estimation and 3D liver imaging from individual X-ray …

Optimizing Uncertainty Quantification Of Vision Transformers In Deep Learning On Novel Ai Architectures, Erik Pautsch, John Li, Silvio Rizzi, George K. Thiruvathukal, Maria Pantoja

Computer Science: Faculty Publications and Other Works

Deep Learning (DL) methods have shown substantial efficacy in computer vision (CV) and natural language processing (NLP). Despite their proficiency, the inconsistency in input data distributions can compromise prediction reliability. This study mitigates this issue by introducing uncertainty evaluations in DL models, thereby enhancing dependability through a distribution of predictions. Our focus lies on the Vision Transformer (ViT), a DL model that harmonizes both local and global behavior. We conduct extensive experiments on the ImageNet-1K dataset, a vast resource with over a million images across 1,000 categories. ViTs, while competitive, are vulnerable to adversarial attacks, making uncertainty estimation crucial for …

Automation Of Crack Detection And Quantification In Civil Infrastructure Facilities Using Deep Learning Techniques, Luqman Ali

Dissertations

Cracks are the earliest signs of structural deterioration that reduce the lifespan and reliability of structures and can lead to severe damage. Assessment and monitoring of the facilities are required for lifetime maintenance and failure prediction. Structure condition information can be obtained manually, i.e., through subjective visual inspection and evaluation by human experts. Manual inspection techniques are labor-intensive, time-consuming, and inspector-dependent, i.e., vulnerable to the inspector’s perceptiveness. Automatic crack detection is crucial at the earliest stage to avoid further structure degradation and allow fast intervention. Deep Learning algorithms have become more popular in crack detection systems in recent years. However, …

Intelligent Computation Offloading In Edge And Cloud Internet Of Vehicles System, Huned Yusufbhai Materwala

Dissertations

The emergence of Internet of Vehicles technology through Vehicular Ad-hoc Networks represents a promising development in the realm of smart city. It empowers the development of smart city applications with a primary focus on improving traffic safety, optimizing traffic flow, and enhancing the overall driving experience. These applications come with demanding quality of service requirements outlined in Service Level Agreements (SLAs). They are communication-intensive, requiring a real-time response, and computation-intensive, demanding high processing. Due to inherent limitations in the computational and storage capacities of vehicles, the system relies on offloading application requests to edge and cloud computing infrastructures. However, the …

Evaluating Methods For Improving Dnn Robustness Against Adversarial Attacks, Laureano Griffin

USF Tampa Graduate Theses and Dissertations

Deep learning has become more widespread as advances in the field continue. As aresult, making sure deep learning is safe has become a priority. A seemingly normal image with intentional pixel changes can cause a well-trained model to misclassify the image with high confidence. Those kinds of images are called adversarial attacks. Adversarial training has been developed to defend against adversarial attacks. This thesis evaluates different adversarial training methods against a variety of adversarial attacks. The key metrics for evaluation are classification accuracy and training time. This thesis also experiments with an improvement on an existing adversarial training method, the …

Semantic Lung Segmentation From Chest X-Ray Images Using Seg-Net Deep Cnn Model, Dathar Abas Hasan, Umed Hayder Jader

Polytechnic Journal

Implementing an accurate image segmentation to extract the lung shape from X-ray images is a vital step in designing a CAD system that diagnoses various types of chest diseases. Lung segmentation is a complex process due to the blurred regions that separate the lung area and the rest of the image. The conventional image segmentation techniques do not meet the ambitions to achieve precise lung segmentation. In this paper, we utilized the Seg-Net semantic segmentation model as a practical approach to distinguish the lung region pixels in X-ray images. The model involves an encoder network that extracts the data from …

Improving Semantic Document Classification Accuracy By Integrating Human-Crafted Knowledge, Zachary Weinfeld, Lubomir Stanchev

College of Engineering Summer Undergraduate Research Program

Document classification is a pivotal task in various domains, warranting the development of robust algorithms. Among these, the Bidirectional Encoder Representations from Transformers (BERT) algorithm, introduced by Google, has proven to perform well when fine-tuned for the task at hand. Leveraging transformer architecture, BERT demonstrates stellar language understanding capabilities. However, the integration of BERT with a range of techniques has shown potential for further enhancing classification accuracy. This work investigates several techniques that leverage semantic understanding to improve the performance of document classification models trained with BERT. Specifically, we explore three methods. First, we will balance corpuses afflicted by imbalanced …

A Self-Configuring Deep Learning Network For Segmentation Of Temporal Bone Anatomy In Cone-Beam Ct Imaging, Andy S Ding, Alexander Lu, Zhaoshuo Li, Manish Sahu, Deepa Galaiya, Jeffrey H Siewerdsen, Mathias Unberath, Russell H Taylor, Francis X Creighton

Faculty, Staff and Student Publications

OBJECTIVE: Preoperative planning for otologic or neurotologic procedures often requires manual segmentation of relevant structures, which can be tedious and time-consuming. Automated methods for segmenting multiple geometrically complex structures can not only streamline preoperative planning but also augment minimally invasive and/or robot-assisted procedures in this space. This study evaluates a state-of-the-art deep learning pipeline for semantic segmentation of temporal bone anatomy.

STUDY DESIGN: A descriptive study of a segmentation network.

SETTING: Academic institution.

METHODS: A total of 15 high-resolution cone-beam temporal bone computed tomography (CT) data sets were included in this study. All images were co-registered, with relevant anatomical structures …

Flacgec: A Chinese Grammatical Error Correction Dataset With Fine-Grained Linguistic Annotation, Hanyue Du, Yike Zhao, Qingyuan Tian, Jiani Wang, Lei Wang, Yunshi Lan, Xuesong Lu

Research Collection School Of Computing and Information Systems

Chinese Grammatical Error Correction (CGEC) has been attracting growing attention from researchers recently. In spite of the fact that multiple CGEC datasets have been developed to support the research, these datasets lack the ability to provide a deep linguistic topology of grammar errors, which is critical for interpreting and diagnosing CGEC approaches. To address this limitation, we introduce FlaCGEC, which is a new CGEC dataset featured with fine-grained linguistic annotation. Specifically, we collect raw corpus from the linguistic schema defined by Chinese language experts, conduct edits on sentences via rules, and refine generated samples manually, which results in 10k sentences …

Sports Item Detection Using Mobilenetv2 With Single Shot Detector, Aiman Haziq Ab Yazik, Siti Nur Kamaliah Kamarudin, Yuzi Mahmud, Azliza Mohd Ali

Malaysian Journal of Computing (MJoC)

Object detection can be applied in various situations and systems. In this research, object detection was specifically applied to build a lending system for tracking the details of sports items in a students' dormitory. The current sports item lending system with a manually recording of data was time consuming, and are more prone to human errors. This inspires the researcher to build a real-time object detection web-based sports item lending system. The system was trained using Single Shot Detector (SSD) with Mobilenet V2 technique to detect the sports item in the warehouse. A total of 960 self-collected sports item image …

Genregait: Gender Recognition Using Gait Features, Yue Fong Ti, Tee Connie, Michael Kah Ong Goh

Journal of Informatics and Web Engineering

Gender recognition based on gait features has gained significant interest due to its wide range of applications in various fields. This paper proposes GenReGait, a robust method for gender recognition utilizing gait features. Gait, the unique walking pattern of individuals, contains distinct gender-specific characteristics, such as stride length, step frequency, and body posture, making it a promising modality for gender estimation. The proposed GenReGait method begins by extracting landmark positions on the human body using a human keypoint estimation technique. These landmarks serve as informative cues for estimating gender based on their spatial and temporal characteristics. However, environmental factors can …

Impact Of Green Building Certification On The Rent Of Commercial Properties: A Review, Thebuwena Arachchige Chandana Hemantha Jayakody, Anthony Vaz

Journal of Informatics and Web Engineering

The world is currently facing two major problems, namely, increasing energy costs and global warming. As a result, it is crucial to take proactive measures to effectively address and mitigate the detrimental impacts arising from elevated energy costs, the pressing issue of global warming, and various types of environmental degradation. As a reaction, international organizations are advocating for the development of eco-friendly, sustainable, or green buildings as a strategy to reduce the harmful effects of the construction sector on the environment. While green development may entail higher costs for developers, it is imperative to evaluate the return on investment from …

Emotion-Aware Music Recommendation, Hieu Tran, Tuan Le, Anh Do, Tram Vu, Steven Bogaerts, Brian T. Howard

Computer Science Faculty publications

It is common to listen to songs that match one's mood. Thus, an AI music recommendation system that is aware of the user's emotions is likely to provide a superior user experience to one that is unaware. In this paper, we present an emotion-aware music recommendation system. Multiple models are discussed and evaluated for affect identification from a live image of the user. We propose two models: DRViT, which applies dynamic routing to vision transformers, and InvNet50, which uses involution. All considered models are trained and evaluated on the AffectNet dataset. Each model outputs the user's estimated valence and arousal …

Gpachov At Checkthat! 2023: A Diverse Multi-Approach Ensemble For Subjectivity Detection In News Articles, Georgi Pachov, Dimitar Dimitrov, Ivan Koychev, Preslav Nakov

Natural Language Processing Faculty Publications

The wide-spread use of social networks has given rise to subjective, misleading, and even false information on the Internet. Thus, subjectivity detection can play an important role in ensuring the objectiveness and the quality of a piece of information. This paper presents the solution built by the Gpachov team for the CLEF-2023 CheckThat! lab Task 2 on subjectivity detection. Three different research directions are explored. The first one is based on fine-tuning a sentence embeddings encoder model and dimensionality reduction. The second one explores a sample-efficient few-shot learning model. The third one evaluates fine-tuning a multilingual transformer on an altered …

Acoustic Waveform Optimization For Three-Dimensional Object Geometries, Justin Ng

Doctoral Dissertations

In recent years, deep learning (DL) has become an increasingly important tool for many different types of classification, identification, and related problems including inverse radar and sonar applications. This thesis studies the degree to which radar and sonar systems may be optimized for DL algorithms in a theoretical setting. Most of the current existing literature found on using DL involve solving a full inverse scattering problem (ISP), that is to determine the properties and/or geometry of the scatter from nearly complete measurements of the scattered field. Methods suitable for use in two-dimensional space have been proposed and demonstrated with varying …

Pattern-Of-Life Modeling With Automatic Dependent Surveillance-Broadcast (Ads-B), Sarah J. Bolton

Theses and Dissertations

This dissertation and research were sponsored by the Air Force Research Laboratory Layered Sensing Exploitation Branch (AFRL/RYA) to investigate the utility of using the data found within aircraft secondary radar to make predictions about aircraft characteristics and intent. The research focuses on making predictions on aircraft characteristics using only the kinetic data within one type of secondary radar, Automatic Dependent Surveillance-Broadcast (ADS-B), as a surrogate for primary radar. The results from this research provide a means to reduce the reliance on a type of aircraft tracking that is vulnerable to cyber attack and other integrity concerns.

Optimization And Application Of Graph Neural Networks, Shuo Zhang

Dissertations, Theses, and Capstone Projects

Graph Neural Networks (GNNs) are widely recognized for their potential in learning from graph-structured data and solving complex problems. However, optimal performance and applicability of GNNs have been an open-ended challenge. This dissertation presents a series of substantial advances addressing this problem. First, we investigate attention-based GNNs, revealing a critical shortcoming: their ignorance of cardinality information that impacts their discriminative power. To rectify this, we propose Cardinality Preserved Attention (CPA) models that can be applied to any attention-based GNNs, which exhibit a marked improvement in performance. Next, we introduce the Directional Node Pair (DNP) descriptor and the Robust Molecular Graph …

Out-Of-Distribution Generalization Of Deep Learning To Illuminate Dark Protein Functional Space, Tian Cai

Dissertations, Theses, and Capstone Projects

Dark protein illumination is a fundamental challenge in drug discovery where majority human proteins are understudied, i.e. with only known protein sequence but no known small molecule binder. It's a major road block to enable drug discovery paradigm shift from single-targeted which looks to identify a single target and design drug to regulate the single target to multi-targeted in a Systems Pharmacology perspective. Diseases such as Alzheimer's and Opioid-Use-Disorder plaguing millions of patients call for effective multi-targeted approach involving dark proteins. Using limited protein data to predict dark protein property requires deep learning systems with OOD generalization capacity. Out-of-Distribution (OOD) …

Learning Representations For Effective And Explainable Software Bug Detection And Fixing, Yi Li

Dissertations

Software has an integral role in modern life; hence software bugs, which undermine software quality and reliability, have substantial societal and economic implications. The advent of machine learning and deep learning in software engineering has led to major advances in bug detection and fixing approaches, yet they fall short of desired precision and recall. This shortfall arises from the absence of a 'bridge,' known as learning code representations, that can transform information from source code into a suitable representation for effective processing via machine and deep learning.

This dissertation builds such a bridge. Specifically, it presents solutions for effectively learning …

Countnet3d: A 3d Computer Vision Approach To Infer Counts Of Occluded Objects With Quantified Uncertainty, Stephen W. Nelson

Theses and Dissertations

3D scene understanding is an important problem that has experienced great progress in recent years, in large part due to the development of state-of-the-art methods for 3D object detection. However, the performance of 3D object detectors can suffer in scenarios where extreme occlusion of objects is present, or the number of object classes is large. In this paper, we study the problem of inferring 3D counts from densely packed scenes with heterogeneous objects. This problem has applications to important tasks such as inventory management or automatic crop yield estimation. We propose a novel regression-based method, CountNet3D, that uses mature 2D …

Sctiger: A Deep-Learning Method For Inferring Gene Regulatory Networks From Case Versus Control Scrna-Seq Datasets., Madison Dautle, Shaoqiang Zhang, Yong Chen

College of Science & Mathematics Departmental Research

Inferring gene regulatory networks (GRNs) from single-cell RNA-seq (scRNA-seq) data is an important computational question to find regulatory mechanisms involved in fundamental cellular processes. Although many computational methods have been designed to predict GRNs from scRNA-seq data, they usually have high false positive rates and none infer GRNs by directly using the paired datasets of case-versus-control experiments. Here we present a novel deep-learning-based method, named scTIGER, for GRN detection by using the co-differential relationships of gene expression profiles in paired scRNA-seq datasets. scTIGER employs cell-type-based pseudotiming, an attention-based convolutional neural network method and permutation-based significance testing for inferring GRNs among …

Early Treatment With Vigabatrin Does Not Decrease Focal Seizures Or Improve Cognition In Tuberous Sclerosis Complex: The Prevent Trial, Elizabeth Martina Bebin, Jurriaan M Peters, Brenda E Porter, Tarrant O Mcpherson, Sarah O'Kelley, Mustafa Sahin, Katherine S Taub, Rajsekar Rajaraman, Stephanie C Randle, William M Mcclintock, Mary Kay Koenig, Mike D Frost, Hope A Northrup, Klaus Werner, Danielle A Nolan, Michael Wong, Jessica L Krefting, Fred Biasini, Kalyani Peri, Gary Cutter, Darcy A Krueger

Faculty, Staff and Student Publications

Objective: This study was undertaken to test the hypothesis that early vigabatrin treatment in tuberous sclerosis complex (TSC) infants improves neurocognitive outcome at 24 months of age.

Methods: A phase IIb multicenter randomized double-blind placebo-controlled trial was conducted of vigabatrin at first epileptiform electroencephalogram (EEG) versus vigabatrin at seizure onset in infants with TSC. Primary outcome was Bayley Scales of Infant and Toddler Development, Third Edition (Bayley-III) cognitive assessment score at 24 months. Secondary outcomes were prevalence of drug-resistant epilepsy, additional developmental outcomes, and safety of vigabatrin.

Results: Of 84 infants enrolled, 12 were screen failures, 4 went straight to …

Enhancing Human Key Point Identification: A Comparative Study Of High-Resolution Vicon Dataset And Coco Dataset Using Bpnet, Bibash Lama

Masters Theses

Accurately identifying human key points is crucial for various applications, including activity recognition, pose estimation, and gait analysis. This study presents a high-resolution dataset created using the VICON motion capture system and three differently oriented 2D cameras, that can be used to train different neural networks for estimating the 2D key joint positions of the person from the 2D images or videos. The participants in the study included 25 healthy adults (17 males and 8 females) performing normal gait movements for about 2 to 3 seconds. The VICON system captured 3D ground truth data, while the three 2D cameras collected …

Deep Learning-Based Cad System For Predicting The Covid-19 X-Ray Images, Aqeel R. Talib, Hana’ M. Ali

Karbala International Journal of Modern Science

According to World Health Organization data, Coronavirus (COVID-19) has infected about 660, 378, 145 patients around the world. It is nonetheless difficult for physicians to detect COVID-19 infections out of CT or X-ray radiographs. Thus, several computer-aided diagnosis (CAD) systems based on deep learning and radiographs were developed to detect COVID-19 infections. However, the majority of approaches considered small datasets, which is ineligible to provide diverse COVID-19 radiographs. This work utilizes a massive number of X-ray radiographs, and compared standard CNN, DenseNet-121, and GoogLeNet for isolating COVID-19 infections out from normal and other pneumonia radiographs. The dataset in this work …

Deep Learning For Automatic Detection And Segmentation From Ct Angiography Of Deep Inferior Epigastric Vascular Structures For Preoperative Planning Of Tram Flap Surgeries, Josephine Chen, Jong Bum Son, Jingfei Ma Phd, Jia Sun, Greg Reece, Miral Patel, Huong Le-Petross Md

Summer Experience 2023

No abstract provided.

Detection Of Internal Voids Of Additively Manufactured Parts With Structual Health Monitoring Methods, David Perez, Berry Lamy, Alireza Modir, Arnaud Casterman, Ibrahim Tansel

Florida Conference on Recent Advances in Robotics

It is possible to create voids inside polymer parts built by additive manufacturing methods. In this study, the feasibility of using structural health monitoring (SHM) methods was evaluated for identification of the voids in polymer parts. The Surface Response to Excitation (SuRE) method was used to collect the experimental data.

Ten Polylactic Acid (PLA) bars of identical external geometries were manufactured using Fused deposition modeling (FDM) type 3D printing. Four bars were solid without any voids inside of them. Two bar groups were manufactured with the same void lengths of 1 mm, 2 mm, and 3 mm at the center. …

Traditional Vs Machine Learning Approaches: A Comparison Of Time Series Modeling Methods, Miguel E. Bonilla Jr., Jason Mcdonald, Tamas Toth, Bivin Sadler

SMU Data Science Review

In recent years, various new Machine Learning and Deep Learning algorithms have been introduced, claiming to offer better performance than traditional statistical approaches when forecasting time series. Studies seeking evidence to support the usage of ML/DL over statistical approaches have been limited to comparing the forecasting performance of univariate, linear time series data. This research compares the performance of traditional statistical-based and ML/DL methods for forecasting multivariate and nonlinear time series.

Training Certified Detectives To Track Down The Intrinsic Shortcuts In Covid-19 Chest X-Ray Data Sets, Ran Zhang, Dalton Griner, John W. Garrett, Zhihua Qi, Guang-Hong Chen

Diagnostic Radiology Articles

Deep learning faces a significant challenge wherein the trained models often underperform when used with external test data sets. This issue has been attributed to spurious correlations between irrelevant features in the input data and corresponding labels. This study uses the classification of COVID-19 from chest x-ray radiographs as an example to demonstrate that the image contrast and sharpness, which are characteristics of a chest radiograph dependent on data acquisition systems and imaging parameters, can be intrinsic shortcuts that impair the model's generalizability. The study proposes training certified shortcut detective models that meet a set of qualification criteria which can …